mcpbeat Sign in

Engrava MCP Server

by sovantica Your server? Claim it
local only

Engrava runs on your own machine — the client starts it, so there is no endpoint to ping. 191 installs a week from pypi. Last commit 3 Oct 2026.

MindQL queries, hybrid search, and a thought graph - read/write memory for AI agents.

Installs per day peak 127 · avg 32 · +7% w/w
a month agotoday
191
Installs / week
pypi · engrava-mcp
1
Stars
0 open issues
3 Oct 2026
Last commit
from GitHub
MIT
License
Python

Nothing serious here today

Today is the operative word: we check Engrava every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add engrava -e 'ENGRAVA_DB_PATH=<ENGRAVA_DB_PATH>' -- uvx engrava-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "engrava": {
      "command": "uvx",
      "args": [
        "engrava-mcp"
      ],
      "env": {
        "ENGRAVA_DB_PATH": "<ENGRAVA_DB_PATH>"
      }
    }
  }
}
~/.codex/config.toml
[mcp_servers.engrava]
command = "uvx"
args = ["engrava-mcp"]
env = { ENGRAVA_DB_PATH = "<ENGRAVA_DB_PATH>" }
.cursor/mcp.json
{
  "mcpServers": {
    "engrava": {
      "command": "uvx",
      "args": [
        "engrava-mcp"
      ],
      "env": {
        "ENGRAVA_DB_PATH": "<ENGRAVA_DB_PATH>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "engrava": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "engrava-mcp"
      ],
      "env": {
        "ENGRAVA_DB_PATH": "<ENGRAVA_DB_PATH>"
      }
    }
  }
}

Put your own value in place of <ENGRAVA_DB_PATH> (Absolute path to the SQLite database file. Created if missing; its directory must exist. Enough on its own: full-text search, the graph and MindQL work, but vector search needs ENGRAVA_MCP_CONFIG). The author’s registry entry marks it as required.

Optional settings from the registry entry, left out of the block above: ENGRAVA_MCP_CONFIG (Absolute path to an engrava.yaml, for an embedding provider (vector search) and the thought/edge journal. When set, it takes precedence and ENGRAVA_DB_PATH is not read), ENGRAVA_MCP_READ_ONLY (Set to true to register no write tools).

Alternatives to Engrava

same job, measured the same way
Cozo Memory
by tobs-code

Local-first memory system for AI agents with hybrid search and graph reasoning

43 installs/wk local only
Reverie
by knowall

Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search

local only
Contextq MCP
by contextq

Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.

267 installs/wk answering
MGI-Mind
by madgodinc

Local memory server for AI agents: hybrid search, a fact graph and a hash-chained audit log.

146 installs/wk local only
MaxGraph
by rumemory

Self-hosted persistent memory for AI agents: knowledge graph and hybrid search.

local only
Neuromcp
by adelelo13

Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation

403 installs/wk local only
Akb
by dnotitia

Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.

54 installs/wk local only
Inkwell
by veronchenko

Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links

local only

Engrava — questions

Answers built from our own checks of this server.

Why is there no uptime for Engrava?
Engrava runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package engrava-mcp was installed 191 times last week.
How do I connect Engrava?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls engrava-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use Engrava?
The pypi package engrava-mcp was installed 191 times in the last week. Week over week that is +7%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Engrava open source?
Yes — it is published under the MIT licence, written in Python and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.